Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/zevtos/agentpipe/fixgit clone --depth 1 https://github.com/zevtos/agentpipeWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00027 | $0.00661 |
| Opus 5 | $0.00014 | $0.00331 |
| Sonnet 5 | $0.00005 | $0.00132 |
| Haiku 4.5 | $0.00003 | $0.00066 |
Grade A, and why
fix scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are orchestrating a bug fix. Be systematic — don't jump to solutions before understanding the root cause.
Context
@CLAUDE.md
Bug Report
$ARGUMENTS
Pipeline
Step 1: Investigate
Before touching any code:
- Reproduce the bug — understand exactly what triggers it
- Read the relevant code paths (use Grep/Glob to find related files)
- Check git blame/log for recent changes in the affected area
- Read error logs if available
- Identify the root cause — not just the symptom
- Check if this is a known pattern (race condition? null reference? off-by-one? missing validation?)
Present your findings:
- Symptom: What the user sees
- Root Cause: Why it happens (be specific — point to exact code)
- Impact: How many users/flows are affected
- Fix Strategy: What needs to change and why
Ask: "Is this the right diagnosis? Should I proceed with this fix approach?" Wait for confirmation.
Step 2: Fix
Implement the fix:
- Make the minimal change that addresses the root cause
- Don't refactor surrounding code — fix the bug only
- Add input validation or guard clauses if the bug was caused by unexpected input
- Add logging if the bug was hard to diagnose (help future debugging)
- Handle the error gracefully if it's an edge case that can't be prevented
Step 3: Review (Reviewer Agent)
Run the reviewer agent:
"Review this bug fix for: $ARGUMENTS
Root cause: [paste root cause from Step 1]
Changes made: [describe the fix]
Verify:
- Does the fix actually address the root cause?
- Does it introduce any regressions?
- Are edge cases handled?
- Is error handling appropriate?
- Could this bug manifest elsewhere? (similar patterns in the codebase)"
If the reviewer finds issues, fix them and re-verify.
Step 4: Regression Test (Tester Agent)
Run the tester agent:
"Write a regression test for this bug: $ARGUMENTS
Root cause: [paste root cause]
The fix: [describe what changed]
Write tests that:
- Reproduce the original bug (this test would have FAILED before the fix)
- Verify the fix works correctly
- Cover related edge cases that could cause similar issues
- Follow existing test patterns in the project"
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 79 lines · 27 tokens per session scan A ceb1c693fd09
fix is a command published in the GitHub repository zevtos/agentpipe (11 stars, last pushed 2mo ago), licensed MIT. It adds 27 tokens to every session and 661 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.